INDEX

Explanations

phrases related to law enforcement actions, particularly raids and searches

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ickets

-0.16

pul

-0.15

chains

-0.15

vey

-0.14

ÑĢÐ¸ÑģÑĤÐ¸

-0.14

umba

-0.14

.IContainer

-0.14

rol

-0.14

iggs

-0.13

 niÃªn

-0.13

POSITIVE LOGITS

ovacÃŃ

0.14

akov

0.14

itol

0.14

gle

0.14

è¶£

0.14

atham

0.13

kdir

0.13

ercial

0.13

Activations Density 0.030%

phrases related to law enforcement actions, particularly raids and searches

No Comments

No Known Activations